基于动态Nelson-Siegel模型的国债收益率曲线预测  

Forecasting the Yield Curve of Chinese Treasury Using Dynamic Nelson-Siegel Model

作　　者：张茂军 汤孝海 赵扬 ZHANG Mao-jun;TANG Xiao-hai;ZHAO Yang(School of Business,Suzhou University of Science and Technology,Suzhou 215009,China)

机构地区：[1]苏州科技大学商学院,江苏苏州215009

出　　处：《经济论坛》2022年第9期81-88,共8页Economic Forum

基　　金：国家自然科学基金项目“基于机器学习方法的企业债券违约智能预警研究”(71961004);苏州科技大学科研启动项目“基于大数据方法的小微企业信用评级研究”(332111801);江苏高校哲学社会科学研究项目“国际贸易新形势下大豆期现货市场价格发现研究”(2020SJA1387)。

摘　　要：预测国债收益率曲线在宏观经济决策中具有非常重要的作用。文章在用动态Nelson-Siegel模型拟合中国债券收益率曲线的基础上,提出了预测收益率曲线的长期、中期、短期因子模型。研究发现,Nelson-Siegel模型拟合中国国债收益率曲线效果显著,长期收益率预测比短期收益率更加精确,线性AR(1)模型更加适合预测收益率曲线的短期和长期变化。Forecasting yield curve of treasury plays a very important role in macroeconomic decision-making.Using dynamic Nelson-Siegel model to fit the yield curve of Chinese treasury,this paper puts forward long-term,medium-term and short-term factor models for forecasting yield curve of Chinese Treasury.It is found that Nelson Siegel model fits yield curve of Chinese treasury significantly,and accuracy of forecasting long-term is better than that of short-term.In addition,linear AR(1)model is more suitable for predicting the short-term and long-term changes of yield curve.

关 键 词：国债 收益率曲线 NELSON-SIEGEL模型 线性AR(1)模型 

分 类 号：F810[经济管理—财政学]